Web-Based Malware Detection System Using Convolutional Neural Network

In this article, we introduce a web-based malware detection system that leverages deep-learning approach. Our primary objective is the development of robust model designed for classifying in executable files. contrast to conventional systems, our approach relies on static techniques unveil true nature files as either malicious or benign. method makes use one-dimensional convolutional neural network 1D-CNN due portable file. Significantly, analysis aligns perfectly with objectives, allowing us uncover features within header. This choice holds particular significance given potential risks associated dynamic detection, often necessitating setup controlled environments, such virtual machines, mitigate dangers. Moreover, seamlessly integrate effective into system, rendering it accessible and user-friendly via web interface. Empirical evidence showcases efficiency proposed methods, demonstrated extensive comparisons state-of-the-art models across three diverse datasets. results undeniably affirm superiority approach, delivering practical, dependable, rapid mechanism identifying